如何将文本分成句子？

#1 楼

import nltk.data

tokenizer = nltk.data.load('tokenizers/punkt/english.pickle')
fp = open("test.txt")
data = fp.read()
print '\n-----\n'.join(tokenizer.tokenize(data))

#2 楼

# -*- coding: utf-8 -*-
import re
alphabets= "([A-Za-z])"
prefixes = "(Mr|St|Mrs|Ms|Dr)[.]"
suffixes = "(Inc|Ltd|Jr|Sr|Co)"
starters = "(Mr|Mrs|Ms|Dr|He\s|She\s|It\s|They\s|Their\s|Our\s|We\s|But\s|However\s|That\s|This\s|Wherever)"
acronyms = "([A-Z][.][A-Z][.](?:[A-Z][.])?)"
websites = "[.](com|net|org|io|gov)"

def split_into_sentences(text):
    text = " " + text + "  "
    text = text.replace("\n"," ")
    text = re.sub(prefixes,"\1<prd>",text)
    text = re.sub(websites,"<prd>\1",text)
    if "Ph.D" in text: text = text.replace("Ph.D.","Ph<prd>D<prd>")
    text = re.sub("\s" + alphabets + "[.] "," \1<prd> ",text)
    text = re.sub(acronyms+" "+starters,"\1<stop> \2",text)
    text = re.sub(alphabets + "[.]" + alphabets + "[.]" + alphabets + "[.]","\1<prd>\2<prd>\3<prd>",text)
    text = re.sub(alphabets + "[.]" + alphabets + "[.]","\1<prd>\2<prd>",text)
    text = re.sub(" "+suffixes+"[.] "+starters," \1<stop> \2",text)
    text = re.sub(" "+suffixes+"[.]"," \1<prd>",text)
    text = re.sub(" " + alphabets + "[.]"," \1<prd>",text)
    if "”" in text: text = text.replace(".”","”.")
    if "\"" in text: text = text.replace(".\"","\".")
    if "!" in text: text = text.replace("!\"","\"!")
    if "?" in text: text = text.replace("?\"","\"?")
    text = text.replace(".",".<stop>")
    text = text.replace("?","?<stop>")
    text = text.replace("!","!<stop>")
    text = text.replace("<prd>",".")
    sentences = text.split("<stop>")
    sentences = sentences[:-1]
    sentences = [s.strip() for s in sentences]
    return sentences

#3 楼

>>> from nltk import tokenize
>>> p = "Good morning Dr. Adams. The patient is waiting for you in room number 3."

>>> tokenize.sent_tokenize(p)
['Good morning Dr. Adams.', 'The patient is waiting for you in room number 3.']

#4 楼

import spacy
nlp = spacy.load('en')

text = '''Your text here'''
tokens = nlp(text)

for sent in tokens.sents:
    print(sent.string.strip())

#5 楼

abbreviations = {'dr.': 'doctor', 'mr.': 'mister', 'bro.': 'brother', 'bro': 'brother', 'mrs.': 'mistress', 'ms.': 'miss', 'jr.': 'junior', 'sr.': 'senior',
                 'i.e.': 'for example', 'e.g.': 'for example', 'vs.': 'versus'}
terminators = ['.', '!', '?']
wrappers = ['"', "'", ')', ']', '}']


def find_sentences(paragraph):
   end = True
   sentences = []
   while end > -1:
       end = find_sentence_end(paragraph)
       if end > -1:
           sentences.append(paragraph[end:].strip())
           paragraph = paragraph[:end]
   sentences.append(paragraph)
   sentences.reverse()
   return sentences


def find_sentence_end(paragraph):
    [possible_endings, contraction_locations] = [[], []]
    contractions = abbreviations.keys()
    sentence_terminators = terminators + [terminator + wrapper for wrapper in wrappers for terminator in terminators]
    for sentence_terminator in sentence_terminators:
        t_indices = list(find_all(paragraph, sentence_terminator))
        possible_endings.extend(([] if not len(t_indices) else [[i, len(sentence_terminator)] for i in t_indices]))
    for contraction in contractions:
        c_indices = list(find_all(paragraph, contraction))
        contraction_locations.extend(([] if not len(c_indices) else [i + len(contraction) for i in c_indices]))
    possible_endings = [pe for pe in possible_endings if pe[0] + pe[1] not in contraction_locations]
    if len(paragraph) in [pe[0] + pe[1] for pe in possible_endings]:
        max_end_start = max([pe[0] for pe in possible_endings])
        possible_endings = [pe for pe in possible_endings if pe[0] != max_end_start]
    possible_endings = [pe[0] + pe[1] for pe in possible_endings if sum(pe) > len(paragraph) or (sum(pe) < len(paragraph) and paragraph[sum(pe)] == ' ')]
    end = (-1 if not len(possible_endings) else max(possible_endings))
    return end


def find_all(a_str, sub):
    start = 0
    while True:
        start = a_str.find(sub, start)
        if start == -1:
            return
        yield start
        start += len(sub)

#6 楼

import re
text = ''.join(open('somefile.txt').readlines())
sentences = re.split(r' *[\.\?!][\'"\)\]]* *', text)

#7 楼

from nltk.tokenize import sent_tokenize
sentence = "As the most quoted English writer Shakespeare has more than his share of famous quotes.  Some Shakespare famous quotes are known for their beauty, some for their everyday truths and some for their wisdom. We often talk about Shakespeare’s quotes as things the wise Bard is saying to us but, we should remember that some of his wisest words are spoken by his biggest fools. For example, both ‘neither a borrower nor a lender be,’ and ‘to thine own self be true’ are from the foolish, garrulous and quite disreputable Polonius in Hamlet."

sent_tokenize(sentence)

#8 楼

def russianTokenizer(text):
    result = text
    result = result.replace('.', ' . ')
    result = result.replace(' .  .  . ', ' ... ')
    result = result.replace(',', ' , ')
    result = result.replace(':', ' : ')
    result = result.replace(';', ' ; ')
    result = result.replace('!', ' ! ')
    result = result.replace('?', ' ? ')
    result = result.replace('\"', ' \" ')
    result = result.replace('\'', ' \' ')
    result = result.replace('(', ' ( ')
    result = result.replace(')', ' ) ') 
    result = result.replace('  ', ' ')
    result = result.replace('  ', ' ')
    result = result.replace('  ', ' ')
    result = result.replace('  ', ' ')
    result = result.strip()
    result = result.split(' ')
    return result

text = 'вы выполняете поиск, используя Google SSL;'
tokens = russianTokenizer(text)

#9 楼

alphabets= "([A-Za-z])"
prefixes = "(Mr|St|Mrs|Ms|Dr)[.]"
suffixes = "(Inc|Ltd|Jr|Sr|Co)"
starters = "(Mr|Mrs|Ms|Dr|He\s|She\s|It\s|They\s|Their\s|Our\s|We\s|But\s|However\s|That\s|This\s|Wherever)"
acronyms = "([A-Z][.][A-Z][.](?:[A-Z][.])?)"
websites = "[.](com|net|org|io|gov|ai|edu|co.uk|ru|info|biz|online)"

#10 楼

# split up a paragraph into sentences
# using regular expressions


def splitParagraphIntoSentences(paragraph):
    ''' break a paragraph into sentences
        and return a list '''
    import re
    # to split by multile characters

    #   regular expressions are easiest (and fastest)
    sentenceEnders = re.compile('[.!?]')
    sentenceList = sentenceEnders.split(paragraph)
    return sentenceList


if __name__ == '__main__':
    p = """This is a sentence.  This is an excited sentence! And do you think this is a question?"""

    sentences = splitParagraphIntoSentences(p)
    for s in sentences:
        print s.strip()

#output:
#   This is a sentence
#   This is an excited sentence

#   And do you think this is a question 

#11 楼

# Very approximate way to split the text into sentences - Break after ? . and !
fullFile = re.sub("(\!|\?|\.) ","\1<BRK>",fullFile)
sentences = fullFile.split("<BRK>");
sentFile = open("./sentences.out", "w+");
for line in sentences:
    sentFile.write (line);
    sentFile.write ("\n");
sentFile.close;

#12 楼

import re

punctuation = re.compile(r"([^\d+])(\.|!|\?|;|\n|。|！|？|；|…|　|!|؟|؛)+")
lines = []

with open('myData.txt','r',encoding="utf-8") as myFile:
    lines = punctuation.sub(r"<pad>", myFile.read())
    lines = [line.strip() for line in lines.split("<pad>") if line.strip()]

#13 楼

from nltk.tokenize import sent_tokenize 
  
text = "Hello everyone. Welcome to GeeksforGeeks. You are studying NLP article"
sent_tokenize(text) 

['Hello everyone.',
 'Welcome to GeeksforGeeks.',
 'You are studying NLP article']

#14 楼

print(sent.string.strip())